arXiv subjects

Cong Li

Publications and source records attributed to Cong Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Multi-Image Visual Token Pruning in Large Visual Language Models

With the growing demand for processing multiple image sequences in real-world applications, various visual token pruning methods have emerged to mitigate the computational and context length constraints faced by Large Vision Language Models (LVLMs). However, most existing pruning approaches rely on static strategies that struggle to adapt across different architectural LVLMs and multi-image scenarios, and are additionally constrained by their dependence on attention computations that are incompatible with efficient techniques like FlashAttention. To address these limitations, we propose a training-free, Adaptive Visual Token Pruning (AVTP) framework, applicable to diverse LVLM architectures. We strategically determine pruning layers based on empirical analysis of visual attention distributions across various LVLMs, and implement adaptive pruning ratios in multi-image contexts where images of higher importance retain proportionally more tokens. We conduct extensive experiments across different LVLMs to demonstrate the effectiveness and robustness of AVTP. Specifically, Qwen3VL-8B achieves 2 times inference speedup while maintaining 96.1\% of its original accuracy on multiple multi-image benchmarks, InternVL3.5-8B retains 94.1\% accuracy, and LLaVA-OV-7B even exceeds its original baseline performance. Our code is available at \href{https://github.com/zry13/AVTP}{this link}.

cs.CV↗

arXiv2026

Dimensionality-induced critical phase transition in stochastic Lotka-Volterra equation: From statistical averaging to systemic tipping point

By analyzing a stochastic Lotka-Volterra (LV) equation, we show that the underlying logic behind the diversity-stability debate in ecology can be framed as a dimensionality-induced critical phase transition, that is, a transition separating the regime dominated by statistical averaging and a systemic tipping point. This phase transition framework unifies the opposing ecological predictions in the diversity-stability debate and sets an intrinsic diversity ceiling for stochastic ecological communities.

q-bio.PE↗

arXiv2026

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-constrained edge devices, Spiking Neural Networks (SNNs) have emerged as a promising alternative to traditional Artificial Neural Networks (ANNs) due to their sparse computing mechanisms and high energy efficiency. However, jointly training ANNs and SNNs exposes a challenge of representational misalignment, which is intrinsically caused by differences in information representation, specifically the semantic gap between continuous real-valued activations in ANNs and discrete spatio-temporal spikes in SNNs. To overcome this barrier, we propose AS-FedBridge, a novel federated learning framework tailored for mixed ANN-SNN clients. AS-FedBridge features a lightweight Bridge equipped with a Pseudo-Spike Interface, which effectively projects continuous signals into a spike-compatible space to facilitate ANN-SNN alignment. Given the absence of existing mixed ANN-SNN federated frameworks, we establish a comprehensive benchmark to evaluate against multiple advanced heterogeneous FL methods. Our empirical analysis demonstrates a positive correlation between the degree of ANN-SNN alignment and the collaborative FL performance. Across four datasets, AS-FedBridge consistently demonstrates advanced accuracy while mitigating extreme scale, architecture, and client heterogeneity challenge. Furthermore, our framework enables a highly controllable trade-off between model performance and resource efficiency. AS-FedBridge accomplishes these robust performance gains while introducing only marginal computational overhead, establishing a robust and practical foundation for mixed ANN-SNN federated learning systems.

cs.LG↗

arXiv2026

COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping

Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred. Existing crop-and-explain methods largely treat explanation as post-hoc text generation and overlook composition, a key aesthetic factor that links crop decisions with interpretable reasoning. In this paper, we reformulate explainable aesthetic image cropping as a structured crop-composition-explanation problem. To support this setting, we introduce COMEX, a new benchmark built through image expansion and an IO-reversal pipeline. COMEX contains 33,161 quadruples, each consisting of an expanded image, a crop box, a composition category, and a composition-grounded explanation, enabling joint learning of crop localization, composition understanding, and explanation generation. We further propose a two-stage SFT+GRPO framework, where supervised fine-tuning establishes the structured output protocol and basic cropping ability, and GRPO further improves crop quality, composition prediction, and explanation faithfulness. We benchmark 15 large vision-language models and existing cropping methods on COMEX, establishing a comprehensive testbed for composition-grounded explainable aesthetic cropping. Experiments on both COMEX and prior benchmarks demonstrate the effectiveness and transferability of our framework, with strong performance across evaluation metrics.

cs.CV↗

arXiv2026

Agentic Harness for Real-World Compilers

Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable automated bug repair, compiler bugs pose unique challenges due to their complexity, deep cross-domain expertise requirements, and sparse, non-descriptive bug reports, necessitating compiler-specific harnesses. To bridge the gap, we introduce llvm-harness, the first harness designed to assist LLM agents in understanding and fixing compiler bugs. Our current focus is on the middle end of LLVM, one of the most widely used compiler infrastructures. Central to llvm-harness are agent-friendly LLVM tools, a benchmark llvm-bench of 334 reproducible LLVM middle-end bugs, and a tailored mini agent llvm-autofix-mini for fixing LLVM middle-end bugs automatically. We evaluate five frontier models and find that they exhibit a performance decline when tackling compiler bugs with the state-of-the-art agent. With llvm-harness' enhancement, their performance improves by 62%. Our specialized mini agent llvm-autofix-mini further outperforms the llvm-harness-enhanced state-of-the-art by 22%. This emphasizes the necessity for specialized harnesses like ours to assist LLMs in compiler engineering tasks. Despite promising results, our expert review also reveals several open challenges that remain when applying LLMs for compiler engineering tasks. GitHub: https://github.com/dtcxzyw/llvm-harness

cs.SE↗

arXiv2026

TAPO: Transition-Aware Policy Optimization for LLM Agents

Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents. However, existing methods predominantly rely on sparse task rewards for policy optimization, failing to fully exploit another class of inherently dense supervisory signals naturally present during online interaction: environmental feedback following action execution. Recent theoretical studies suggest that generalization in multi-step, goal-oriented tasks hinges on predictive knowledge of environmental consequences. Inspired by this, we propose TAPO: Transition-Aware Policy Optimization for LLM Agents, a unified training framework that alternates between policy optimization and transition supervision. Beyond standard RL updates, TAPO repurposes rollout data to apply action-conditioned next-observation prediction supervision on a shared backbone model. This approach enhances the model's sensitivity to environmental transition dynamics and action consequences while concurrently optimizing the policy. It serves as a computationally lightweight, plug-and-play enhancement module for existing agent RL algorithms, requiring no additional expert data, extra sampling costs, or inference-time overhead. We conduct systematic experiments on WebShop and ALFWorld, integrating foundation models of various scales with different policy optimization algorithms. Empirical results demonstrate that TAPO consistently improves task performance over pure policy optimization baselines.

cs.LG↗

arXiv2026

Hydrogen-induced lattice cohesion weakening favors atomic displacement

Atomic displacement -- the fundamental process underlying diverse deformation and damage phenomena in metals, from irradiation defect production to stress-driven dislocation motion -- is governed by interatomic cohesion strength. Here, lattice-dissolved hydrogen (LDH) occurring in metals under direct hydrogen exposure is identified to effectively weaken lattice cohesion, and thereby facilitating atomic displacement and dislocation movement upon plastic deformation in sub-threshold stress regime. This atomic-scale insight provides a physically transparent mechanism for hydrogen-enhanced localized plasticity implicated in hydrogen embrittlement. We quantitatively verify the hydrogen-induced lattice cohesion weakening effect on metal surfaces exposed to low-energy hydrogen plasma, where massive defects are generated despite the absence of sufficient ion momentum for direct displacement damage. By unprecedentedly quantifying the cohesion-weakening effect of LDH independently from defect-trapped H, we establish a new paradigm to understand hydrogen embrittlement.

cond-mat.mtrl-sci↗

arXiv2026

CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation

Deploying Video Diffusion Models (VDMs) on edge devices is appealing for localized and privacy-preserving generation, but their iterative Transformer-based denoising remains too slow for practical local inference. Cross-Timestep Caching (CTC) has emerged as a promising direction for reducing redundant computation, reusing activations across adjacent denoising steps rather than modifying model weights, while largely preserving generation fidelity. However, on memory-constrained edge GPUs, CTC requires a massive cache footprint that quickly exceeds on-device VRAM and forces the cache into host memory. More fundamentally, cache operators remain tightly interleaved and chain-dependent with native compute operators, so naive near-memory offloading still incurs repeated PCIe exchanges for residual and fusion computations, turning cache reuse into a communication- and serialization-bound execution flow. We therefore propose CODA, an algorithm-hardware co-designed architecture centered on Compute-Cache Operator Disaggregation. CODA separates dense compute paths and memory-bound cache paths across the xPU and a lightweight DIMM-side near-memory engine, reorganizes fragmented cache activity into hardware-friendly coalesced segments, and exploits Classifier-Free Guidance (CFG) branch independence to overlap xPU compute with cache-side execution. Experiments show that CODA achieves up to 1.80x end-to-end speedup and 1.74x higher energy efficiency, while preserving competitive generation quality compared with a state-of-the-art caching algorithm.

cs.AR↗

arXiv2026

Model-Independent and Data-Driven Extraction of the Photon Distribution Function at the Electron--Ion Collider

In this work, we investigate a cross-section-ratio-based inversion method for extracting distribution functions at the Electron--Ion Collider (EIC). Starting from the general factorization formula $dσ= H \otimes f$, we show that, for an appropriate bremsstrahlung process and suitably chosen differential observables, the convolution structure can be reduced to a multiplicative form. On this basis, we define the ratio $R = \frac{dσ_{\mathrm{exp}}}{dσ_{\mathrm{hard}}},$ where $dσ_{\mathrm{exp}}$ is the experimentally measured differential cross section and $dσ_{\mathrm{hard}}$ is a perturbatively calculable theoretical input. We then establish the relation between $R$ and the target distribution function $f$. Finally, we investigate how the theoretical input $dσ_{\mathrm{hard}}$ should be constructed when soft-photon radiation, finite-bin-width effects, and experimental acceptance are taken into account.

hep-ph↗

arXiv2026

A neuromorphic vision system for open-world visual intelligence

Time-efficient and robust visual intelligence remains a critical challenge in unstructured open-world environments, yet current approaches often rely on computationally intensive neural architectures or task-specific sensors with limited versatility. Inspired by biological vision and information bottleneck theory, we report a neuromorphic vision system that performs task-oriented visual intelligence through an information distillation strategy (named as task traction mechanism) implemented on hardware. The system integrates a polarization-sensitive imager with a resistive random-access memory (RRAM) array to progressively distill task-relevant information via light field selection, region of interest extraction, and target anticipation. The neuromorphic vision system conducts visual tasks within an execution time of 193 μs. Evaluation across eight challenging open-world scenarios shows accuracy improvements of 25.54%, 37.73%, and 36.10% for object tracking, object segmentation, and trajectory prediction, respectively, together with an average 30.6-fold reduction in latency relative to state-of-the-art solutions.

eess.IV↗

arXiv2026

Complete Next-to-Next-to-Leading-Order QCD Correction to $J/ψ\to 3γ$ Decay

We address the long-standing problem of negative decay and production rates in perturbative QCD for exclusive processes by proposing amplitude-level NRQCD factorization as a systematic prescription. Building on this, we present the first complete next-to-next-to-leading-order (NNLO) QCD correction to the decay $J/ψ\to 3γ$. The resulting partial width, $Γ(J/ψ\to 3γ) = 0.96^{+4.32}_{-0.13}$ eV, combines this NNLO contribution with the known up to $\mathcal{O}(α_s v^2)$ relativistic correction and shows markedly improved agreement with the high-precision BESIII measurement. In the same way, $Γ(Υ\to 3γ) = 0.0086^{+0.0028}_{-0.0006}$ eV is obtained. The dominant theoretical uncertainty originates from the renormalization scale variation, underscoring the challenge of perturbative convergence at this order and the necessity for future higher-order calculations.

hep-ph↗

arXiv2026

Stress-triggered atomic explosion of trapped hydrogen initiates crack nucleation

Hydrogen embrittlement (HE) has persisted for more than a century as one of the most intractable problems in materials science. The prevailing view1 that diffusive H governs embrittlement has fostered the widespread assumption that H trapping at crystal defects mitigates HE. Here we overturn this conventional paradigm. Using plasma/ion irradiation of tungsten, we decouple -- for the first time -- H-induced crack nucleation from subsequent cavity propagation, and reveal nucleation as a two-stage mechanochemical fracture instability enabled by trapped H in the absence of diffusive H. In the first stage, H accumulation to a critical occupancy at dislocation cores acts as a chemical fuse, collapsing the local cohesive strength to a threshold at which infinitesimal external loads can trigger atomic decohesion. This bond rupture instantaneously enables the second stage: confined recombination of atomic hydrogen into molecular form. The abrupt release of chemical energy within an atomically restricted volume generates a transient inflation pressure that drives a dynamic, brittle jump to an internal macroscopic cavity. By separating mechanical decohesion triggering from energetic crack driving, our results provide a deterministic framework for the onset of H-induced crack nucleation under low-stress conditions. Furthermore, we place experimentally the classical H-enhanced decohesion model on an atomistic foundation and elevate it from phenomenology to prediction. Finally, by shifting the focus from experimentally elusive diffusive H to directly measurable trapped H, this work reframes HE as a deterministic, quantifiable instability, establishing a new paradigm for understanding and mitigating H-induced failure in high-strength metals.

cond-mat.mtrl-sci↗

arXiv2026

Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations

Soft-bodied organisms such as octopuses and elephant trunks exhibit remarkable morphological adaptability, dynamically reconfiguring body shape and stiffness, and flexibly adjusting their control strategies to enable versatile behaviors. Inspired by these biological systems, various soft robots have emerged in recent decades, featuring diverse materials, stiffnesses, and morphologies tailored to specific tasks. Despite substantial advances in the materials and structural designs of soft robots, developing a generalizable control framework capable of rapid adaptation across diverse configurations remains a long-standing challenge. Existing controllers are limited to fixed configurations, demanding laborious configuration-specific remodelling and policy redesign for new configurations. Here, we introduce a generalizable control system that enables rapid adaptation across diverse soft robot configurations via reinforcement learning in a shared linear Koopman embedding space. By encoding robot dynamics into this embedding space, our method decouples control policies from specific morphologies, allowing real-time, model-free policy adaptation across diverse configurations without retraining from scratch. We validate our system across 33 distinct robot configurations. Our system achieves a 75 times reduction in transfer samples across configurations, while sustaining robust performance under high-speed motion, heavy payloads, and multiactuator faults, and achieving real-world skills previously unattainable in soft robotics. This work establishes a unified and adaptable control paradigm for diverse soft robot configurations, bridging mechanical reconfigurability with control flexibility, and may offer broader insights for generalizable control in complex physical systems.

cs.RO↗

arXiv2026

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlying this deficiency. Our motivation stems from an unexpected observation: text embeddings tend to align with frequent but uninformative tokens when projected onto the vocabulary space. We argue that this excessive expression of high-frequency tokens suppresses the model's ability to capture nuanced semantics. To address this, we introduce EmbedFilter, a simple linear transformation designed to refine text embeddings derived from LLMs directly. Specifically, we uncover that the unembedding matrix within LLMs encodes a latent space that is actively writing these frequent tokens into embedding space. By filtering out this subspace, EmbedFilter suppress the influence of high-frequency tokens, thereby enhancing semantic representations. As a compelling byproduct, this enables an inherent dimensionality reduction, lowering index storage and speedup retrieval while fully preserving the refined embedding quality. Our experiments across multiple LLM backbones demonstrate that LLMs equipped with EmbedFilter achieve superior zero-shot downstream performance even with significantly reduced embedding dimensions. We hope our findings provide deeper insights into the mechanisms of LLM-based representations and inspire more principled designs to improve text embeddings training. Our code is available at https://github.com/CentreChen/EmbFilter.

cs.CL↗

arXiv2026

Accelerating NBTI Aging Evaluation via Physics-Aware Graph Attention Networks

As semiconductor technology advances to smaller nodes, Negative Bias Temperature Instability (NBTI) under prolonged workloads has emerged as a significant bottleneck constraining reliability-aware Design-Technology Co-Optimization (DTCO). Conventional TCAD simulations incur prohibitive computational overhead when evaluating device aging characteristics, making it difficult to satisfy the demand for efficient iterative design cycles. To address this challenge, this paper proposes an aging evaluation framework based on a physics-aware graph attention network (Physics-Aware RelGAT). By losslessly mapping unstructured device meshes into attributed graphs, this framework constructs a 45-dimensional device encoding scheme that integrates interface trap distributions and macroscopic electro-thermal stresses, achieving a direct mapping from underlying physical quantities to device degradation characteristics. To overcome the challenge of predicting currents that span multiple orders of magnitude, a dual-end normalization strategy and a log-scale loss function optimization are introduced, ensuring the model possesses high-precision fitting capabilities. Experimental results demonstrate that the model achieves a mean error of only 1.27% on an independent test set, achieving an acceleration of approximately 17,000 times compared to traditional TCAD simulations. This framework provides a solution for the assessment of circuit reliability in advanced process nodes that successfully balances physical fidelity with industrial-grade efficiency.

cs.ET↗

arXiv2026

Nanoscale Polar Landscapes in Quantum Paraelectric SrTiO3

SrTiO3 is a textbook quantum paraelectric, with ferroelectricity purportedly suppressed by quantum fluctuations of ionic positions down to the lowest temperatures. The precise real space structure of SrTiO3 at low temperature, however, has remained undefined despite decades of study. Here we directly image the low-temperature polar structure of quantum parelectric SrTiO3, using cryogenic scanning transmission electron microscopy down to 20 K. High resolution imaging reveals a spatially fluctuating landscape of nanoscale domains of finite polarization. The short-range polar domains first grow and self-organize into a periodic structure over tens of nanometers. However, the process reverses when entering the quantum paraelectric regime below 40 K and the periodically ordered polar nanodomains fragment into small clusters.

cond-mat.mtrl-sci↗

arXiv2026

Entanglement redistribution of hyperon-antihyperon pair via sequential decay

Hyperon-antihyperon pairs produced in high energy electron-positron annihilation constitute a naturally spin-entangled system in the high energy regime. Recently, a probabilistic amplification of entanglement, termed autodistillation, has been found in the daughter baryon-antibaryon pairs from hyperon decay and is constrained by an upper boundary. This work demonstrates that the quantum entanglement in this process may be accompanied by a decrease, constrained by a lower boundary, but will not be completely lost. Thus, the entanglement of these systems undergoes redistribution within the phase space during the sequential decays of hyperons, highlighting an important role of hyperon polarization. By using the explicit spin density matrix of baryon pairs, it is also found that quantumness of the system characterized by quantum discord always have the possibility to increase during decay processes, even when entanglement evaluated by concurrence and negativity does not increase.

hep-ph↗

arXiv2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.

cs.CV↗